English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large language models (LLMs) have become mainstream technology with theirversatile use cases and impressive performance. Despite the countlessout-of-the-box applications, LLMs are still not reliable. A lot of work isbeing done to improve the factual accuracy, consistency, and ethical standardsof these models through fine-tuning, prompting, and Reinforcement Learning withHuman Feedback (RLHF), but no systematic analysis of the responses of thesemodels to different categories of statements, or on their potentialvulnerabilities to simple prompting changes is available. In this work, weanalyze what confuses GPT-3: how the model responds to certain sensitive topicsand what effects the prompt wording has on the model response. We find thatGPT-3 correctly disagrees with obvious Conspiracies and Stereotypes but makesmistakes with common Misconceptions and Controversies. The model responses areinconsistent across prompts and settings, highlighting GPT-3's unreliability.Dataset and code of our analysis is available inhttps://github.com/tanny411/GPT3-Reliability-Check.

Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording